© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95713
    Prev
    Next
    INDEX
    Explanations

    references to employment and workforce characteristics across various industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oker
    -0.07
    anka
    -0.07
    á»iji
    -0.06
    ût
    -0.06
    iej
    -0.06
    Ñīин
    -0.06
    oul
    -0.06
    aced
    -0.06
    liga
    -0.06
     cuff
    -0.06
    POSITIVE LOGITS
    çĮ
    0.07
     sectors
    0.06
    fits
    0.06
     sector
    0.06
    immel
    0.06
     Ngh
    0.06
    ãĥ¼ãĥĦ
    0.06
    orton
    0.06
     whe
    0.06
    odos
    0.06
    Activations Density 0.032%

    No Known Activations